Monte Carlo Methods

#RL #Learning #computer-science #Control We want to go one step further than DP algorithms. Here, we do not assume complete knowledge of the environment. Monte Carlo methods require only experience—sample sequences of states, actions, and rewards from actual or simulated interaction with an environment. At their core, Monte Carlo methods are ways of solving the reinforcement learning problem based on averaging sample returns. Monte Carlo methods sample and average returns for each state-action pair and average rewards for each action. Note that B=because all the action selections are undergoing learning, the problem becomes nonstationary from the point of view of the earlier state.

Sources:

1. Reinforcement Learning: An Introduction by Sutton